© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 15093
    Prev
    Next
    INDEX
    Explanations

    references to PlayStation consoles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific PlayStation console models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Austrian
    -0.72
    butt
    -0.71
     Israeli
    -0.69
     adm
    -0.69
     ç¥ŀ
    -0.65
     Lithuan
    -0.64
     Yemeni
    -0.64
    ãĥĥ
    -0.64
     Samoa
    -0.64
    abwe
    -0.64
    POSITIVE LOGITS
    atile
    0.98
    ombat
    0.93
    PS
    0.89
    weet
    0.89
    icket
    0.88
    Ħ¢
    0.88
    DP
    0.86
    UV
    0.85
    ega
    0.83
    ilon
    0.82
    Activations Density 0.006%

    No Known Activations